Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity

Researchers have extended the CNF framework to solve multi-variable and non-linear partial differential equations, addressing computational challenges in scientific simulations. The work focuses on improving PDE solvers for forward solutions, inverse problems, and equation discovery with self-tuning techniques and benchmark evaluations.

• →Extension of CNF framework solver to handle multi-dependent-variable and non-linear PDE settings.
• →Research addresses curse of dimensionality and high computation costs in numerical PDE methods.
• →Work includes applications for forward solutions, inverse problems, and equation discovery.
• →Implementation features self-tuning techniques and evaluation on benchmark problems.
• →Provides comprehensive survey of neural PDE solvers for scientific simulation applications.